Update app.py

app.py

@@ -5,7 +5,7 @@ import os
 import re
 from PyPDF2 import PdfReader
 
-# ========== TRANSCRIPT PARSING FUNCTIONS ==========
+# ========== TRANSCRIPT PARSING FUNCTIONS (UPDATED) ==========
 
 def parse_transcript(file):
     if file.name.endswith('.csv'):
@@ -21,29 +21,62 @@ def parse_transcript(file):
     else:
         return "Unsupported file format", None
 
-    courses = df['Course'].tolist() if 'Course' in df.columns else []
-    grades = df['Grade'].tolist() if 'Grade' in df.columns else []
-    gpa = df['GPA'].mean() if 'GPA' in df.columns else "N/A"
-
-    course_info = "\n".join([f"{c}: {g}" for c, g in zip(courses, grades)])
-    return f"Transcript Parsed:\n\n{course_info}\n\nGPA: {gpa}", {
-        "courses": courses,
-        "grades": grades,
-        "gpa": gpa
+    # Extract GPA (try multiple possible column names)
+    gpa = "N/A"
+    for col in ['GPA', 'Grade Point Average', 'Cumulative GPA']:
+        if col in df.columns:
+            gpa = df[col].iloc[0] if isinstance(df[col].iloc[0], (float, int)) else "N/A"
+            break
+
+    # Extract grade level (try multiple possible column names)
+    grade_level = "N/A"
+    for col in ['Grade Level', 'Grade', 'Class', 'Year']:
+        if col in df.columns:
+            grade_level = df[col].iloc[0]
+            break
+
+    # Extract courses (current and past)
+    courses = []
+    for col in ['Course', 'Subject', 'Course Name', 'Class']:
+        if col in df.columns:
+            courses = df[col].tolist()
+            break
+
+    # Create output display
+    output_text = f"Grade Level: {grade_level}\nGPA: {gpa}\n\nCourses:\n"
+    output_text += "\n".join(f"- {course}" for course in courses)
+
+    return output_text, {
+        "gpa": gpa,
+        "grade_level": grade_level,
+        "courses": courses
     }
 
 def extract_info_from_pdf(text):
-    course_lines = re.findall(r"([A-Za-z &]+):\s*([A-F][+-]?)", text)
-    gpa_match = re.search(r"GPA[:\s]+(\d\.\d+)", text)
-    courses = [course.strip() for course, _ in course_lines]
-    grades = [grade for _, grade in course_lines]
-    gpa = float(gpa_match.group(1)) if gpa_match else "N/A"
-
-    course_info = "\n".join([f"{c}: {g}" for c, g in zip(courses, grades)])
-    return f"Transcript Parsed (PDF):\n\n{course_info}\n\nGPA: {gpa}", {
-        "courses": courses,
-        "grades": grades,
-        "gpa": gpa
+    # Extract GPA
+    gpa_match = re.search(r"(GPA|Grade Point Average)[:\s]+(\d\.\d+)", text, re.IGNORECASE)
+    gpa = float(gpa_match.group(2)) if gpa_match else "N/A"
+
+    # Extract grade level
+    grade_match = re.search(r"(Grade|Year)[:\s]+(\d+|Freshman|Sophomore|Junior|Senior)", text, re.IGNORECASE)
+    grade_level = grade_match.group(2) if grade_match else "N/A"
+
+    # Extract courses - improved pattern to catch more course formats
+    course_pattern = r"""
+        (?:[A-Z]{2,}\s?\d{3})          # Course codes like 'MATH 101' or 'ENG101'
+        |[A-Z][a-z]+(?:\s[A-Z][a-z]+)*  # Or full course names
+    """
+    courses = re.findall(course_pattern, text, re.VERBOSE)
+    courses = list(set(courses))  # Remove duplicates
+
+    # Create output display
+    output_text = f"Grade Level: {grade_level}\nGPA: {gpa}\n\nCourses:\n"
+    output_text += "\n".join(f"- {course}" for course in courses)
+
+    return output_text, {
+        "gpa": gpa,
+        "grade_level": grade_level,
+        "courses": courses
     }
 
 # ========== LEARNING STYLE QUIZ FUNCTION ==========
@@ -98,7 +131,8 @@ def save_profile(name, age, interests, transcript, learning_style, favorites, bl
 def transcript_display(transcript_dict):
     if not transcript_dict:
         return "No transcript uploaded."
-    return "\n".join([f"{c}: {g}" for c, g in zip(transcript_dict["courses"], transcript_dict["grades"])] + [f"GPA: {transcript_dict['gpa']}"])
+    return "\n".join([f"- {course}" for course in transcript_dict["courses"]] + 
+                     [f"Grade Level: {transcript_dict['grade_level']}", f"GPA: {transcript_dict['gpa']}"])
 
 # ========== GRADIO INTERFACE ==========
 
@@ -141,7 +175,7 @@ with gr.Blocks() as app:
     with gr.Tab("Step 4: Save & Review"):
         output_summary = gr.Markdown()
         save_btn = gr.Button("Save Profile")
-        
+
         def gather_and_save(name, age, interests, movie, movie_reason, show, show_reason,
                             book, book_reason, character, character_reason, blog, transcript, learning_style):
             favorites = {
@@ -162,10 +196,4 @@ with gr.Blocks() as app:
                                transcript_data, learning_output],
                        outputs=output_summary)
 
-app.launch()
-
-   
-
-    
-    
-  
+app.launch()